Provides containerization support for the MCP server, enabling deployment as a Docker container with specified environment variables and configuration.
Uses Mermaid diagrams to visualize the architecture and data flow between the user, agent, container, and database.
Built on Python 3.11+, serving as the foundation for the MCP server implementation that connects to Microsoft SQL Server databases.
MSSQL MCP Server
This project is an MCP (Model Context Protocol) server for connecting to Microsoft SQL Server databases. It uses MCPO to introduce an OpenAPI proxy in front of the MCP server, enabling OpenAPI-compatible clients to interact with the MCP server via a standardized HTTP interface. The server provides tools for schema inspection and querying, all accessible via the MCP protocol or through the OpenAPI proxy.
Diagram
Related MCP server: Supabase MCP Server
Features
Connects to Microsoft SQL Server using MCP
Provides tools for querying and schema inspection
Designed for integration with MCP-compatible clients
Container-ready (Docker)
Available Tools
read_query: Execute SELECT queries on the MSSQL database
list_tables: List all existing tables and their columns
Required Environment Variables
Set the following environment variables to configure the database connection:
MSSQL_SERVER(name.database.windows.net)MSSQL_DATABASE(Name)MSSQL_USER(Username)MSSQL_PASSWORD(Password)MCP_SERVER_NAME(mcp-database-assistant)MCP_SERVER_VERSION(1.0.0)APPLICATIONINSIGHTS_CONNECTION_STRING(InstrumentationKey=...)
These can be set in your environment or injected at container runtime.
Building and Running with Docker
Build the Docker image:
docker build -t mssql-mcp .Run the container:
docker run --rm -it mssql-mcpDefault command: The container runs:
mcpo --config config.json
Requirements
Python 3.11+
Microsoft ODBC Driver 17 for SQL Server (installed in the Docker image)
MCP-compatible client (for example, VS Code with MCP extension)
License
See LICENSE.